thermograph/tests/test_notify.py

"""Tests for the subscription evaluation engine: trigger detection and message
wording (pure logic), plus an integration check that a full pass fetches a MISSING
archive once but never re-fetches a cached one (against conftest's throwaway DB)."""
import datetime
import types
import uuid

import numpy as np
import polars as pl

import climate
import db
import notify
from models import Notification, Subscription, User
from sqlalchemy import delete, select


def _history() -> pl.DataFrame:
    start, end = datetime.date(1990, 1, 1), datetime.date(2020, 12, 31)
    dates = [start + datetime.timedelta(days=i) for i in range((end - start).days + 1)]
    rng = np.random.default_rng(1)
    n = len(dates)
    return pl.DataFrame({
        "date": dates,
        "doy": np.array([d.timetuple().tm_yday for d in dates], dtype="int16"),
        "tmax": 70 + rng.normal(0, 8, n),
        "tmin": 48 + rng.normal(0, 7, n),
        "precip": rng.exponential(0.05, n),
    })


def _sub(**kw):
    d = dict(metrics=["tmax"], threshold=95, two_sided=False, kind="observed",
             label="Testville", lat=1.0, lon=2.0)
    d.update(kw)
    return types.SimpleNamespace(**d)


def _row(date, **vals):
    r = {"date": datetime.date.fromisoformat(date)}
    r.update(vals)
    return r


def test_high_trigger():
    row = _row("2021-07-15", tmax=115.0, tmin=50.0, precip=0.0)
    hit = notify._first_trigger(_sub(metrics=["tmax"], threshold=95), [row], _history(), {})
    assert hit is not None
    _, metric, direction, g = hit
    assert metric == "tmax" and direction == "high" and g["percentile"] >= 95


def test_no_trigger_when_normal():
    row = _row("2021-07-15", tmax=70.0, tmin=48.0, precip=0.0)
    assert notify._first_trigger(_sub(metrics=["tmax"], threshold=95), [row], _history(), {}) is None


def test_low_trigger_only_when_two_sided():
    row = _row("2021-07-15", tmax=70.0, tmin=10.0, precip=0.0)   # extreme low overnight
    assert notify._first_trigger(
        _sub(metrics=["tmin"], threshold=95, two_sided=False), [row], _history(), {}) is None
    hit = notify._first_trigger(
        _sub(metrics=["tmin"], threshold=95, two_sided=True), [row], _history(), {})
    assert hit is not None and hit[1] == "tmin" and hit[2] == "low"


def test_precip_never_low_side():
    # A dry day has no rain-percentile, so a precip subscription never fires low
    # even when two-sided (rain is one-directional).
    row = _row("2021-07-15", tmax=70.0, precip=0.0)
    assert notify._first_trigger(
        _sub(metrics=["precip"], threshold=95, two_sided=True), [row], _history(), {}) is None


def test_compose_observed_wording():
    g = {"percentile": 99.0, "value": 115.0, "grade": "Near Record"}
    title, body = notify._compose(_sub(kind="observed", label="Phoenix"),
                                  "2026-07-14", "tmax", "high", g)
    assert title == "Phoenix: unusually hot day"
    assert body.startswith("On 2026-07-14")
    assert "99th percentile" in body and "Near Record" in body


def test_compose_forecast_wording():
    g = {"percentile": 2.0, "value": 5.0, "grade": "Near Record"}
    title, body = notify._compose(_sub(kind="forecast", label="Nome"),
                                  "2026-01-02", "tmin", "low", g)
    assert title == "Nome: unusually cold night"
    assert body.startswith("Forecast for 2026-01-02")


# --- integration: on-demand archive fetch during a full pass -----------------
def _recent_extreme(today):
    dates = [today - datetime.timedelta(days=1), today]
    return pl.DataFrame({
        "date": dates,
        "doy": np.array([d.timetuple().tm_yday for d in dates], dtype="int16"),
        "tmax": [72.0, 115.0],   # today's high is an extreme -> should trigger
        "tmin": [48.0, 48.0],
        "precip": [0.0, 0.0],
    })


def _seed_single_subscription(cell_id="100_200"):
    db.Base.metadata.create_all(db.sync_engine)
    uid = uuid.uuid4()
    with db.sync_session_maker() as s:
        s.execute(delete(User))          # clean slate in the throwaway DB
        s.commit()
        s.add(User(id=uid, email="pass@example.com", hashed_password="x", is_active=True))
        s.commit()
        s.add(Subscription(user_id=uid, cell_id=cell_id, label="X", lat=1.0, lon=2.0,
                           threshold=95, metrics=["tmax"], kind="observed", two_sided=False))
        s.commit()
    return uid


def _user_notifications(uid):
    with db.sync_session_maker() as s:
        return s.execute(
            select(Notification).where(Notification.user_id == uid)
        ).scalars().all()


def test_missing_archive_is_fetched_once(monkeypatch):
    uid = _seed_single_subscription()
    fetched = []
    monkeypatch.setattr(climate, "load_cached_history", lambda cell: None)
    monkeypatch.setattr(climate, "get_history",
                        lambda cell: (fetched.append(cell["id"]) or (_history(), {})))
    monkeypatch.setattr(climate, "get_recent_forecast",
                        lambda cell: _recent_extreme(datetime.date.today()))
    notify.run_pass()
    assert fetched, "a subscribed cell with no cached archive should be fetched once"
    assert len(_user_notifications(uid)) == 1


def test_cached_archive_is_never_refetched(monkeypatch):
    uid = _seed_single_subscription()
    fetched = []
    monkeypatch.setattr(climate, "load_cached_history", lambda cell: _history())
    monkeypatch.setattr(climate, "get_history",
                        lambda cell: (fetched.append(cell["id"]) or (_history(), {})))
    monkeypatch.setattr(climate, "get_recent_forecast",
                        lambda cell: _recent_extreme(datetime.date.today()))
    notify.run_pass()
    assert not fetched, "a cached archive must never be re-fetched by the evaluator"
    assert len(_user_notifications(uid)) == 1